← Search

Mingze Zhong

2 accepted papers

2026

Investigating Social Bias Propagation in Federated Fine-tuning of Large Language Models

AAAI 2026technical

Large language models (LLMs) have achieved remarkable success in many domains, but concerns about data quality and privacy are growing. Federated Learning (FL) offers a privacy-preserving solution by training a model on local clients without sharing data. However, the impact of biased private data o

Cited by 0SourcePDFScholar
2025

Spiral of Silence in Large Language Model Agents

EMNLP 2025

The Spiral of Silence (SoS) theory holds that individuals with minority views often refrain from speaking out for fear of social isolation, enabling majority positions to dominate public discourse. When the “agents” are large language models (LLMs), however, the classical psychological explanation i

Cited by 0SourcePDFScholar